# Omazy CX

> Omazy CX answers for your business. It reads what you already publish,
> replies to customers on your site and in your channels, and hands over to
> a human when it should. This file maps the documentation for models.

Every link below is raw markdown. Append `.md` to any page URL on this site
to get the same. The full corpus in one file is at /llms-full.txt.

## Get started

- [Get started](https://docs.omazy.ai/start.md): What Omazy CX is, how a workspace, an app and an agent fit together, and what to do in your first hour.
- [Your first agent](https://docs.omazy.ai/start/first-agent.md): From an empty workspace to an agent that answers, in about half an hour.
- [Put it on your site](https://docs.omazy.ai/start/first-widget.md): Install the widget, decide what it shows before anyone types, and go live.

## Agent

- [Agent](https://docs.omazy.ai/agent.md): The brief, knowledge, help center, catalog, prompts, saved responses, testing and publishing.
- [Writing the brief](https://docs.omazy.ai/agent/brief.md): The brief is the agent's job description. It composes into the system prompt, so this is the file that matters.
- [Adding knowledge](https://docs.omazy.ai/agent/knowledge.md): What the agent can answer from: crawled pages, uploaded documents, and the authored answers that do the real work.

## Widget

- [Widget](https://docs.omazy.ai/widget.md): The chat widget on your site: a 6KB loader, a hosted chat app, and a host API for talking to it from your own code.
- [Host API](https://docs.omazy.ai/widget/host-api.md): Drive the widget from your own JavaScript. Commands, events, and identity.
- [Message blocks](https://docs.omazy.ai/widget/message-blocks.md): The building blocks an agent can put on screen: text, quick replies, buttons, cards, carousels, forms and more.
- [Troubleshooting](https://docs.omazy.ai/widget/troubleshooting.md): When the launcher does not appear, opens blank, or behaves differently on mobile.

## Engage

- [Engage](https://docs.omazy.ai/engage.md): Inbox, conversations, customers, journeys and broadcast.
- [Working the inbox](https://docs.omazy.ai/engage/inbox.md): Picking up a handover, what the agent already tried, and closing the loop so it does not happen twice.

## Connect

- [Connect](https://docs.omazy.ai/connect.md): Channels, the chat widget, and integrations with the tools you already run.
- [Channels and integrations](https://docs.omazy.ai/connect/channels.md): Connecting the other places customers message you, and the tools you already run.
- [Connect an AI assistant](https://docs.omazy.ai/connect/mcp.md): Connect Claude or any MCP client to one business, so it can read and change your agent, knowledge, catalog and widget.

## Automate

- [Automate](https://docs.omazy.ai/automate.md): Runbooks, automations, tasks, events, the data store, plugins and webhooks.
- [Runbooks and approvals](https://docs.omazy.ai/automate/runbooks.md): Multi-step procedures the agent can run, and the approval step that keeps the expensive ones reversible.

## Insights

- [Insights](https://docs.omazy.ai/insights.md): Reports and analytics on what your agent resolved, what it escalated, and where it struggled.
- [Reading the reports](https://docs.omazy.ai/insights/reading-reports.md): Which numbers mean something, which ones mislead, and what to change on Monday.

## Workspace

- [Workspace](https://docs.omazy.ai/workspace.md): Team and roles, billing and plan, LLM providers, audit and security.
- [Roles and permissions](https://docs.omazy.ai/workspace/roles.md): Who can do what, and how to give people the narrowest role that lets them work.

## API

- [API](https://docs.omazy.ai/reference/api.md): HTTP endpoint reference for the Omazy CX middleware.
- [Authentication](https://docs.omazy.ai/reference/api/authentication.md): Install-scoped bearer tokens, how they are minted, and how to revoke one machine without signing out the rest.
- [Conventions](https://docs.omazy.ai/reference/api/conventions.md): The response envelope, pagination, and the rules that hold across every endpoint.

## CLI

- [CLI](https://docs.omazy.ai/reference/cli.md): Install the omazy binary, sign in, and drive your workspace from the terminal.
- [Profiles and scoping](https://docs.omazy.ai/reference/cli/profiles.md): How the CLI decides which workspace and app a command applies to, and how to stop guessing.
- [Command reference](https://docs.omazy.ai/reference/cli/commands.md): Every command in the omazy CLI, generated from the binary's own help output.

## SDK

- [SDK](https://docs.omazy.ai/reference/sdk.md): The Python plugin SDK. Build a plugin that adds tools, prompts, automations and webhooks to an Omazy workspace.
- [Your first plugin](https://docs.omazy.ai/reference/sdk/first-plugin.md): From pip install to a tool the agent can call, in about fifteen minutes.

## LLM Gateway

- [LLM Gateway](https://docs.omazy.ai/reference/llm-gateway.md): One door to every model provider, with budgets, guards and per-call cost recorded on the way through.
- [Providers and models](https://docs.omazy.ai/reference/llm-gateway/providers.md): Connecting a model provider, choosing a model, and what happens when one is unavailable.

## Platform

- [Platform](https://docs.omazy.ai/reference/platform.md): Architecture, the response envelope, auth, rate limits, error codes and versioning.
- [Error codes](https://docs.omazy.ai/reference/platform/error-codes.md): Every error code the platform emits, what triggers it, and what to do about it.
- [MCP server](https://docs.omazy.ai/reference/platform/mcp-server.md): The workspace MCP server: transport, OAuth discovery and authorization, the access model, and every tool with its arguments and required role.